Robot Localization Using Non-Unique Wall Landmarks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Autonomous mobile robots face challenges in localization and mapping without relying on expensive and complex "at-a-distance" sensors like cameras or LIDAR, particularly in using adjacency sensors to create and distinguish non-unique landmark features for navigation.
Innovation Solution
The use of adjacency sensors, such as bump force sensors and short-range infrared sensors, to create and recognize landmark features, combined with motion sensor data, allows for robot localization and mapping without the need for "at-a-distance" sensors, enabling the use of non-unique landmarks like straight wall segments for re-localization during missions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cameras or LIDAR sensors are used for robot localization and mapping, then measurement precision and reliability are improved, but device complexity and cost increase
Solution Approach 1:
The patent replaces expensive, complex sensors (cameras, LIDAR) with inexpensive adjacency sensors (bump sensors, wall-following sensors) that detect landmarks only when in direct contact or immediate proximity. This substitution maintains functional capability for localization while dramatically reducing sensor cost and complexity, accepting that each sensor is simple and short-range but sufficient for the task
Solution Approach 2:
The patent substitutes optical and electromagnetic sensing systems (cameras, LIDAR) with mechanical contact-based sensing (bump sensors, wall-following sensors). The mechanical adjacency sensors detect landmarks through direct physical contact or near-contact, replacing the need for complex optical processing and distance measurement systems
2Device complexity
If adjacency sensors are used instead of cameras or LIDAR, then device complexity and cost are reduced, but measurement precision and reliability deteriorate
Solution Approach 1:
The patent combines multiple simple adjacency sensor measurements with robot motion data through data association algorithms. By merging sequential observations of the same landmark from different positions and angles, the system accumulates sufficient information for accurate localization, compensating for the limited precision of individual adjacency sensor readings
Solution Approach 2:
The patent performs preliminary mapping during a first mission, storing landmark characteristics (position, orientation, geometry) in advance. During subsequent missions, the robot can quickly localize by comparing current adjacency sensor readings against this pre-built map, improving localization speed and reliability without requiring complex real-time sensing
3Adaptability or versatility
If non-unique landmarks are used for localization, then adaptability is improved, but measurement precision deteriorates
Solution Approach 1:
The patent resolves landmark ambiguity by incorporating multiple dimensions of information: position, orientation, and geometric characteristics. When a robot encounters a straight wall segment, the system doesn't rely solely on the wall's presence but also on its orientation relative to the robot's motion, its position in the map, and its geometric properties, creating a multi-dimensional signature that distinguishes non-unique landmarks
Solution Approach 2:
The patent uses feedback from robot motion and sequential observations to disambiguate non-unique landmarks. As the robot moves and repeatedly observes the same landmark from different positions and angles, the system accumulates feedback that confirms the landmark's identity and refines the localization estimate, even when the landmark appears identical to others in the environment
Data Source
AI summary
Robot localization or mapping can be provided without requiring the expense or complexity an “at-a-distance” sensor, such as a camera, a LIDAR sensor, or the like. Adjacency-derived landmark features can be used and non-unique landmark features can be accommodated. Uncertainty in robot pose can be tracked and compared to an adaptive threshold, and non-dock and docks based localization behavior can be controlled based on the uncertainty, the adaptive threshold, one or more other thresholds, and the accessibility of available differently oriented landmark features, such as perpendicularly oriented straight wall segments landmark features. Available features can be sorted according to a quality metric, and path planning and navigation techniques are also included for helping obtain successful wall-following and localization observations.